Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to organization and structure

    oai_token-act-pair · gpt-3.5-turbo

    repeated punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onite
    -0.67
     Fortress
    -0.61
    iership
    -0.60
     convertible
    -0.60
     Mechdragon
    -0.59
     resonance
    -0.59
    enegger
    -0.58
    Desk
    -0.58
     immersion
    -0.58
     locals
    -0.57
    POSITIVE LOGITS
     ."
    1.27
     .
    1.23
     .)
    1.15
     ..
    1.04
    -.
    1.03
     ._
    0.95
    _.
    0.89
    ,.
    0.88
    `.
    0.85
    shut
    0.80
    Act Density 0.019%

    No Known Activations